Instructions to use deepseek-ai/deepseek-vl2-small with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use deepseek-ai/deepseek-vl2-small with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("image-text-to-text", model="deepseek-ai/deepseek-vl2-small")
messages = [
    {
        "role": "user",
        "content": [
            {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/p-blog/candy.JPG"},
            {"type": "text", "text": "What animal is on the candy?"}
        ]
    },
]
pipe(text=messages)

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("deepseek-ai/deepseek-vl2-small", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use deepseek-ai/deepseek-vl2-small with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "deepseek-ai/deepseek-vl2-small"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "deepseek-ai/deepseek-vl2-small",
		"messages": [
			{
				"role": "user",
				"content": [
					{
						"type": "text",
						"text": "Describe this image in one sentence."
					},
					{
						"type": "image_url",
						"image_url": {
							"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
						}
					}
				]
			}
		]
	}'

Use Docker

docker model run hf.co/deepseek-ai/deepseek-vl2-small

SGLang

How to use deepseek-ai/deepseek-vl2-small with SGLang:

Install from pip and serve model

# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
    --model-path "deepseek-ai/deepseek-vl2-small" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "deepseek-ai/deepseek-vl2-small",
		"messages": [
			{
				"role": "user",
				"content": [
					{
						"type": "text",
						"text": "Describe this image in one sentence."
					},
					{
						"type": "image_url",
						"image_url": {
							"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
						}
					}
				]
			}
		]
	}'

Use Docker images

docker run --gpus all \
    --shm-size 32g \
    -p 30000:30000 \
    -v ~/.cache/huggingface:/root/.cache/huggingface \
    --env "HF_TOKEN=<secret>" \
    --ipc=host \
    lmsysorg/sglang:latest \
    python3 -m sglang.launch_server \
        --model-path "deepseek-ai/deepseek-vl2-small" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "deepseek-ai/deepseek-vl2-small",
		"messages": [
			{
				"role": "user",
				"content": [
					{
						"type": "text",
						"text": "Describe this image in one sentence."
					},
					{
						"type": "image_url",
						"image_url": {
							"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
						}
					}
				]
			}
		]
	}'

Docker Model Runner
How to use deepseek-ai/deepseek-vl2-small with Docker Model Runner:
```
docker model run hf.co/deepseek-ai/deepseek-vl2-small
```

deepseek-vl2-small / config.json

doubility123

Upload folder using huggingface_hub

c5b2dc5 verified almost 2 years ago

Raw History Blame Contribute Delete

2.07 kB

{
  "candidate_resolutions": [
    [
      384,
      384
    ],
    [
      384,
      768
    ],
    [
      768,
      384
    ],
    [
      384,
      1152
    ],
    [
      1152,
      384
    ],
    [
      384,
      1536
    ],
    [
      1536,
      384
    ],
    [
      768,
      768
    ],
    [
      384,
      1920
    ],
    [
      1920,
      384
    ],
    [
      384,
      2304
    ],
    [
      2304,
      384
    ],
    [
      768,
      1152
    ],
    [
      1152,
      768
    ],
    [
      384,
      2688
    ],
    [
      2688,
      384
    ],
    [
      384,
      3072
    ],
    [
      3072,
      384
    ],
    [
      768,
      1536
    ],
    [
      1536,
      768
    ],
    [
      384,
      3456
    ],
    [
      3456,
      384
    ],
    [
      1152,
      1152
    ]
  ],
  "global_view_pos": "head",
  "language_config": {
    "architectures": [
      "DeepseekV2ForCausalLM"
    ],
    "auto_map": {
      "AutoConfig": "configuration_deepseek.DeepseekV2Config",
      "AutoModel": "modeling_deepseek.DeepseekV2Model",
      "AutoModelForCausalLM": "modeling_deepseek.DeepseekV2ForCausalLM"
    },
    "first_k_dense_replace": 1,
    "hidden_size": 2048,
    "intermediate_size": 10944,
    "lm_head": true,
    "max_position_embeddings": 4096,
    "model_type": "deepseek_v2",
    "moe_intermediate_size": 1408,
    "n_group": 1,
    "n_routed_experts": 64,
    "n_shared_experts": 2,
    "num_attention_heads": 16,
    "num_experts_per_tok": 6,
    "num_hidden_layers": 27,
    "num_key_value_heads": 16,
    "q_lora_rank": null,
    "rm_head": false,
    "topk_group": 1,
    "topk_method": "greedy",
    "torch_dtype": "bfloat16"
  },
  "model_type": "deepseek_vl_v2",
  "projector_config": {
    "model_type": "mlp_projector"
  },
  "tile_tag": "2D",
  "torch_dtype": "bfloat16",
  "transformers_version": "4.38.2",
  "vision_config": {
    "layers": 27,
    "mlp_ratio": 3.7362,
    "model_name": "siglip_so400m_patch14_384",
    "model_type": "vision",
    "patch_size": 14,
    "width": 1152
  }
}

	{
	"candidate_resolutions": [
	[
	384,
	384
	],
	[
	384,
	768
	],
	[
	768,
	384
	],
	[
	384,
	1152
	],
	[
	1152,
	384
	],
	[
	384,
	1536
	],
	[
	1536,
	384
	],
	[
	768,
	768
	],
	[
	384,
	1920
	],
	[
	1920,
	384
	],
	[
	384,
	2304
	],
	[
	2304,
	384
	],
	[
	768,
	1152
	],
	[
	1152,
	768
	],
	[
	384,
	2688
	],
	[
	2688,
	384
	],
	[
	384,
	3072
	],
	[
	3072,
	384
	],
	[
	768,
	1536
	],
	[
	1536,
	768
	],
	[
	384,
	3456
	],
	[
	3456,
	384
	],
	[
	1152,
	1152
	]
	],
	"global_view_pos": "head",
	"language_config": {
	"architectures": [
	"DeepseekV2ForCausalLM"
	],
	"auto_map": {
	"AutoConfig": "configuration_deepseek.DeepseekV2Config",
	"AutoModel": "modeling_deepseek.DeepseekV2Model",
	"AutoModelForCausalLM": "modeling_deepseek.DeepseekV2ForCausalLM"
	},
	"first_k_dense_replace": 1,
	"hidden_size": 2048,
	"intermediate_size": 10944,
	"lm_head": true,
	"max_position_embeddings": 4096,
	"model_type": "deepseek_v2",
	"moe_intermediate_size": 1408,
	"n_group": 1,
	"n_routed_experts": 64,
	"n_shared_experts": 2,
	"num_attention_heads": 16,
	"num_experts_per_tok": 6,
	"num_hidden_layers": 27,
	"num_key_value_heads": 16,
	"q_lora_rank": null,
	"rm_head": false,
	"topk_group": 1,
	"topk_method": "greedy",
	"torch_dtype": "bfloat16"
	},
	"model_type": "deepseek_vl_v2",
	"projector_config": {
	"model_type": "mlp_projector"
	},
	"tile_tag": "2D",
	"torch_dtype": "bfloat16",
	"transformers_version": "4.38.2",
	"vision_config": {
	"layers": 27,
	"mlp_ratio": 3.7362,
	"model_name": "siglip_so400m_patch14_384",
	"model_type": "vision",
	"patch_size": 14,
	"width": 1152
	}
	}